{"id":"https://openalex.org/W2161130530","doi":"https://doi.org/10.1109/robot.2005.1570365","title":"The Strategy Entropy of Reinforcement Learning for Mobile Robot Navigation in Complex Environments","display_name":"The Strategy Entropy of Reinforcement Learning for Mobile Robot Navigation in Complex Environments","publication_year":2006,"publication_date":"2006-01-18","ids":{"openalex":"https://openalex.org/W2161130530","doi":"https://doi.org/10.1109/robot.2005.1570365","mag":"2161130530"},"language":"en","primary_location":{"id":"doi:10.1109/robot.2005.1570365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2005.1570365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 IEEE International Conference on Robotics and Automation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008999201","display_name":"Xiaodong Zhuang","orcid":"https://orcid.org/0000-0001-6508-8507"},"institutions":[{"id":"https://openalex.org/I73142707","display_name":"Athens University of Economics and Business","ror":"https://ror.org/03s262162","country_code":"GR","type":"education","lineage":["https://openalex.org/I73142707"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"X. Zhuang","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, HIEST University, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, HIEST University, Athens, Greece","institution_ids":["https://openalex.org/I73142707"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5008999201"],"corresponding_institution_ids":["https://openalex.org/I73142707"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.14013511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"5","issue":null,"first_page":"1742","last_page":"1747"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7599965333938599},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.6600964069366455},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.6557946801185608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6543940305709839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5642246007919312},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5237966775894165},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49369749426841736},{"id":"https://openalex.org/keywords/mobile-robot-navigation","display_name":"Mobile robot navigation","score":0.421791136264801},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4156869053840637},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.31756865978240967}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7599965333938599},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.6600964069366455},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.6557946801185608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6543940305709839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5642246007919312},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5237966775894165},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49369749426841736},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.421791136264801},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4156869053840637},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.31756865978240967},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robot.2005.1570365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2005.1570365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 IEEE International Conference on Robotics and Automation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1580890024","https://openalex.org/W1610678877","https://openalex.org/W1612579644","https://openalex.org/W1979071892","https://openalex.org/W2093266575","https://openalex.org/W2107726111","https://openalex.org/W2154803134","https://openalex.org/W2160371091","https://openalex.org/W2396715201","https://openalex.org/W3020831056","https://openalex.org/W6683821272","https://openalex.org/W6711916277"],"related_works":["https://openalex.org/W2122735287","https://openalex.org/W2080635515","https://openalex.org/W1540467731","https://openalex.org/W1886477626","https://openalex.org/W2175869054","https://openalex.org/W2419867673","https://openalex.org/W167006473","https://openalex.org/W2175714038","https://openalex.org/W2803104311","https://openalex.org/W2724299411"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"the":[3,19,41,45,49,53,68,80,92],"concept":[4],"of":[5,18,48],"entropy":[6,24,31,95],"is":[7,32,64,77],"introduced":[8],"into":[9],"reinforcement":[10],"learning":[11,42,54,58,62,82,89,98,101,104],"for":[12,40],"mobile":[13],"robot":[14],"control.":[15],"The":[16,28,84],"definitions":[17],"local":[20,69,93],"and":[21],"global":[22,29],"strategy":[23,30,70,94],"are":[25],"proposed":[26,65,81],"respectively.":[27],"proved":[33],"to":[34],"be":[35],"a":[36,56],"quantitative":[37],"problem-independent":[38],"measurement":[39],"progress,":[43],"i.e.":[44],"convergence":[46],"degree":[47],"strategy.":[50],"To":[51],"improve":[52],"performance,":[55],"new":[57],"algorithm":[59],"with":[60,79,102],"self-adaptive":[61],"rate":[63],"based":[66,90],"on":[67,91],"entropy.":[71],"Robot":[72],"navigation":[73],"in":[74],"multi-obstacle":[75],"environments":[76],"achieved":[78],"algorithm.":[83],"experimental":[85],"results":[86],"show":[87],"that":[88],"has":[96],"better":[97],"performance":[99],"than":[100],"fixed":[103],"rates.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}